Training-Free Guidance for Discrete Diffusion Models for Molecular Generation
This work addresses a gap in enabling flexible guidance for discrete data in molecular generation, though it appears incremental as it adapts existing continuous methods to a discrete setting.
The paper tackled the problem of applying training-free guidance to discrete diffusion models for molecular generation, demonstrating the method's ability to guide data generation using functions like atom type proportion and molecular weight.
Training-free guidance methods for continuous data have seen an explosion of interest due to the fact that they enable foundation diffusion models to be paired with interchangable guidance models. Currently, equivalent guidance methods for discrete diffusion models are unknown. We present a framework for applying training-free guidance to discrete data and demonstrate its utility on molecular graph generation tasks using the discrete diffusion model architecture of DiGress. We pair this model with guidance functions that return the proportion of heavy atoms that are a specific atom type and the molecular weight of the heavy atoms and demonstrate our method's ability to guide the data generation.